@article{lavidadrivevisiontextinteractionvlmfor,
  title = {LaVida Drive: Vision-Text Interaction VLM for Autonomous Driving with Token Selection, Recovery and Enhancement},
  author = {Siwen Jiao and Yangyi Fang and Baoyun Peng and Wangqun Chen and Bharadwaj Veeravalli},
  year = {2024},
  eprint = {2411.12980},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2411.12980v2},
}